© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6020
    Prev
    Next
    INDEX
    Explanations

    references to various professions and their roles within collaborative environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    lists of professional groups or job categories.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     variation
    -0.39
    variation
    -0.34
     volume
    -0.29
     aufzu
    -0.29
     naps
    -0.28
     Variation
    -0.28
    pre
    -0.28
    Kamer
    -0.28
     dosis
    -0.28
    Variation
    -0.27
    POSITIVE LOGITS
    protoimpl
    0.78
     للمعارف
    0.77
     ſch
    0.66
     MainAxisSize
    0.66
    OGND
    0.63
     stakeholders
    0.62
     indígen
    0.62
     queſta
    0.61
     increí
    0.61
    ſelves
    0.61
    Activations Density 0.218%

    No Known Activations